CPPF: A contextual and post-processing-free model for automatic speech recognition

TL;DR

The paper introduces CPPF, a novel ASR model that integrates multiple post-processing tasks directly into the recognition process, eliminating the need for separate post-processing steps and reducing error propagation.

Contribution

This work presents CPPF, a unified ASR model that incorporates contextual and post-processing tasks, streamlining the pipeline and enhancing recognition accuracy without additional post-processing.

Findings

CPPF effectively integrates multiple tasks without performance loss.

The model reduces multi-stage pipeline complexity.

It prevents cascading errors in speech recognition.

Abstract

ASR systems have become increasingly widespread in recent years. However, their textual outputs often require post-processing tasks before they can be practically utilized. To address this issue, we draw inspiration from the multifaceted capabilities of LLMs and Whisper, and focus on integrating multiple ASR text processing tasks related to speech recognition into the ASR model. This integration not only shortens the multi-stage pipeline, but also prevents the propagation of cascading errors, resulting in direct generation of post-processed text. In this study, we focus on ASR-related processing tasks, including Contextual ASR and multiple ASR post processing tasks. To achieve this objective, we introduce the CPPF model, which offers a versatile and highly effective alternative to ASR processing. CPPF seamlessly integrates these tasks without any significant loss in recognition performance.